1,720,985 research outputs found
Evaluation of deep learning with long short-term memory networks for time series forecasting in supply chain management
Full text linkPerformance analysis and forecasting the evolution of complex systems are two challenging tasks in manufacturing. Time series data from complex systems capture the dynamic behaviors of the underlying processes. However, non-linear and non-stationary dynamics pose a major challenge for accurate forecasting. To overcome statistical complexities through analyzing time series, we approach the problem with deep learning methods. In this paper, we mainly focus on the long short-term memory (LSTM) networks for demand forecasts in supply chain management, where the future demand for a certain product is the basis for the respective replenishment systems. This study contributes to the literature by conducting experiments on real data to investigate the potential of using LSTM networks for final customer demand forecasting, and hence for increasing the overall value generated by a supply chain. Both forward LSTM and bidirectional LSTM (forward-backward) for short-and long-term demand prediction in supply chain management are considered in this study
Optimizing Healthcare Ecosystem Performance-A Computational Study of Integrated Patient Assistance in Primary Care
Full text linkHome health care professionals provide medical services to patients in their homes. With rising demand, it’s crucial to manage operational costs effectively while ensuring satisfaction for patients. This study presents a bi-objective optimization model aimed at resolving routing and scheduling challenges in home health care, with a focus on both system efficiency and patient accessibility. A Mixed-Integer Linear Programming Model (MILP) is developed. To tackle computational time challenges, we propose a Non-dominated Sorting Genetic Algorithm II to solve the multi-objective optimization problems. The evaluation of Pareto fronts demonstrates the method’s efficiency. We apply the method in a real-world case study to provide managerial implications
Fault diagnosis by multisensor data: A data-driven approach based on spectral clustering and pairwise constraints
Full text linkThis paper deals with clustering based on feature selection of multisensor data in high-dimensional space. Spectral clustering algorithms are efficient tools in signal processing for grouping datasets sampled by multisensor systems for fault diagnosis. The effectiveness of spectral clustering stems from constructing an embedding space based on an affinity matrix. This matrix shows the pairwise similarity of the data points. Clustering is then obtained by determining the spectral decomposition of the Laplacian graph. In the manufacturing field, clustering is an essential strategy for fault diagnosis. In this study, an enhanced spectral clustering approach is presented, which is augmented with pairwise constraints, and that results in efficient identification of fault scenarios. The effectiveness of the proposed approach is described using a real case study about a diesel injection control system for fault detection
Finite Mixture Models for Clustering Auto-Correlated Sales Series Data Influenced by Promotions
Full text linkThe focus of the present paper is on clustering, namely the problem of finding distinct groups in a dataset so that each group consists of similar observations. We consider the finite mixtures of regression models, given their flexibility in modeling heterogeneous time series. Our study aims to implement a novel approach, which fits mixture models based on the spline and polynomial regression in the case of auto-correlated data, to cluster time series in an unsupervised machine learning framework. Given the assumption of auto-correlated data and the usage of exogenous variables in the mixture model, the usual approach of estimating the maximum likelihood parameters using the Expectation–Maximization (EM) algorithm is computationally prohibitive. Therefore, we provide a novel algorithm for model fitting combining auto-correlated observations with spline and polynomial regression. The case study of this paper consists of the task of clustering the time series of sales data influenced by promotional campaigns. We demonstrate the effectiveness of our method in a case study of 131 sales series data from a real-world company. Numerical outcomes demonstrate the efficacy of the proposed method for clustering auto-correlated time series. Despite the specific case study of this paper, the proposed method can be used in several real-world application fields
A numerical procedure for machining distortions simulation on a SAF 2507 casting workpiece
No full textThe workpiece distortion that occurs during machining, can lead to a large increase in the number of the scrap parts. Residual stresses are the main cause of these distortions and they are generally present in both forging and casting products. In order to obtain the desired microstructure and mechanical properties, the workpiece is subjected to heat treatment before being worked. Quenching produces residual stresses that exist throughout a large percentage of the casting or forging part. Distortion occurs as a result of removing stressed material from the workpiece. The component will re-equilibrate and distort as each layer of stressed material is machined away. This paper describes a procedure development for distortions numerical analysis on a SAF2507 casting bulk workpiece. A solubilization heat treatment has been simulated, in order to predict the bulk residual stresses distribution. Different metal cutting processes have been considered to measure the numerical distortions induced in the workpiece
Utilizing Mixture Regression Models for Clustering Time-Series Energy Consumption of a Plastic Injection Molding Process
Full text linkConsidering the issue of energy consumption reduction in industrial plants, we investigated a clustering method for mining the time-series data related to energy consumption. The industrial case study considered in our work is one of the most energy-intensive processes in the plastics industry: the plastic injection molding process. Concerning the industrial setting, the energy consumption of the injection molding machine was monitored across multiple injection molding cycles. The collected data were then analyzed to establish patterns and trends in the energy consumption of the injection molding process. To this end, we considered mixtures of regression models given their flexibility in modeling heterogeneous time series and clustering time series in an unsupervised machine learning framework. Given the assumption of autocorrelated data and exogenous variables in the mixture model, we implemented an algorithm for model fitting that combined autocorrelated observations with spline and polynomial regressions. Our results demonstrate an accurate grouping of energy-consumption profiles, where each cluster is related to a specific production schedule. The clustering method also provides a unique profile of energy consumption for each cluster, depending on the production schedule and regression approach (i.e., spline and polynomial). According to these profiles, information related to the shape of energy consumption was identified, providing insights into reducing the electrical demand of the plant
IC.IDO as a tool for displaying machining processes. The logic interface between computer-aided-manufacturing and virtual reality
Full text linkThis scientific communication investigates the logic interface of a CAM solver, i.e., MasterCAM, into a Virtual Reality (VR) environment. This integration helps in displaying machining operations in virtual reality. Currently, to partially visualize the results of a simulation in an immersive environment, an import/export procedure must be done manually. Here, a software plugin integrated into IC.IDO (by ESI Group) has been realized and fully described. This application allows the complete integration of CAM solver into the VR environment. In particular, the VERICUT solver has been integrated into VR. This kind of integration has never been done yet
Thermal characterization methodology for dry finishing turning of SAF 2507 stainless steel based on finite element simulations and surrogate models
Full text linkThis paper addresses the numerical thermal characterization of a 3D turning process of a SAF 2507 stainless steel. A thermographic test campaign was conducted to measure the temperature distribution at the tool-workpiece interface. The campaign was accommodated by means of a L18 fractional factorial design of experiment. The 3D turning process was simulated using the software TWS Advantedge. The heat transfer numerical coefficients were calibrated against experimental measures to obtain temperature values as accurate as possible. A statistical methodology framework was adopted to study the dependence of the coefficients from the machining parameters. A heat transfer surrogate model was then built and next experimentally validated
Shape factors and feasibility of sheet metal hydroformed components
No full textThe authors have investigated, in another paper, the problem related to the definition of a "set of shape factors" in order to declare the feasibility of a product through sheet hydroforming. In particular the defined shape factors are three different a-dimensional coefficients by which it is possible to declare the feasibility of a product through the calculation, in different sections, of the three previous shape factors. The robustness of this methodology is related to the correct calculation of the "limit value" of each shape factor. In fact the feasibility is reached if, in any section, the calculated shape factors are higher than their respective limit values. In this paper the authors have performed an extensive numerical and experimental campaign, taking into account a different geometry respect to that of the first paper, in order to: re-calculate the limit value for each shape factor and, then, verify the correctness of the limit values exposed in the previous first paper. The numerical campaign has been used, after the evaluation of the accuracy of the numerical model, in order to study the feasibility of the product without engaging the hydroforming machine. Finite Element Analysis (FEA) has been extensively used in order to investigate and define each shape factor with a proper comparison to the macro feasibility of the chosen component geometry. The limit values that have been calculated by the authors in this paper are slightly different from those calculated in the first paper. From this point of view it is possible that, although the shape factors are a-dimensional coefficients, they are affected by different choices of the users as, for example, the dimensions of the initial blank. Anyway, the small differences in the shape factors limit values do not adversely affect the use of the shape factors in order to predict the feasibility of the product
Experimental thermographic investigation for dry finish turning of SAF 2507 steel
No full textThe Oil&Gas Industry widely uses Super-Duplex Stainless Steels (S-DSS) since their combination of high mechanical characteristics and corrosion resistance. Among them, the SAF 2507 is one of the renowned. The challenges associated with the machining of these steels are directly related to the high temperature that influences the tool-life and the quality of the finished products. This phenomenon is induced by the low thermal conductivity which leads to a high concentration of heat. In order to properly understand their thermal behavior, the distribution of the temperature varying the cutting parameters should be investigated. During dry finish turning, the evolution of the temperature can be captured through a thermographic test campaign, for instance following a L18 - 2 · 37-5 fractional factorial design with no replications. The data acquired can be deeply studied with a statistical methodology framework, the relationship between the response of the experiment and the machining parameters can be established, and a surrogate model for predicting the temperature can be built and validated. The results show that, for the SAF 2507 steel, the cutting temperature for dry finishing turning is mostly influenced by the deep of cut, the feed rate and slightly by the cutting speed
- …
